I’m interested in hosting something like this, and I’d like to know experiences regarding this topic.
The main reason to host this for privacy reasons and also to integrate my own PKM data (markdown files, mainly).
Feel free to recommend me videos, articles, other Lemmy communities, etc.
Programming is my main use case for LLMs and I think it’s too slow right now. In the 30 seconds it takes a local llama to give me an answer I’ve already figured it out.
I’m definitely keeping an eye on it though. Our org is really interesting in training models on our code base and customer data.
It’s good for me because I’m piss poor at programming. In my defense, I’m not a programmer or even programmer adjacent. I do see how it wouldn’t be useful to a pro. It also has occasionally given me garbage advice that an expert would spot right away while I had to figure out in my own that it was ‘hallucinating’ again. There’s nothing better for learning than troubleshooting, though!
I can absolutely see it getting useful for a pro. It’s already a better version of IDE templates. If you have to write boilerplate code this can already do that. It’s a huge time saver for the things you’d have to go look up to remember how to do and piece together yourself.
Example: today I wanted a quick way to serve my current working directory over HTTP so I could do some quick web work. I asked ChatGPT to write me a bash function I could stick in my profile to do this, and I told it to pick a random unused port. That would have taken me much longer had I went to lookup how to do that all. The only hint I gave it was to use the Python builtin module for serving http.
Don’t get me wrong, I use copilot and it’s super handy, especially for menial things. I just don’t have all day to wait for a local llm to spit out an answer.
I was using ollama + code llama + continue extension in vscode. The answers are pretty decent, but yeah, too slow and no inline suggestions. I think (not an expert) a machine with a graphics card would be more performant, but we can’t just build a suitable pc for 100 engineers.
I also don’t own the code so privacy isn’t my concern lol so copilot suits my needs just fine.
I’ve found it’s pretty good for translating between steps so to speak.
Converted some bash to python relatively quickly by giving it snippets and fixing errors as it made them.
I also had success generating an ansible playbook based on my own previously written install instructions for SillyTavern and llama.cpp.
I could do both of those tasks myself, but thar would be more difficult than having a mostly correct translation and fixing some errors.
You should make sure you are running a model that fits in your vram, for me it runs faster than any online LLM I’ve tried.